{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-monkeytyping-solution-to-the-youtube-8m","title":"The Monkeytyping Solution to the YouTube-8M Video Understanding Challenge","arxiv_id":"1706.05150","date":"2017-06-16","proceeding":null,"authors":["He-Da Wang","Teng Zhang","Ji Wu"],"abstract":"This article describes the final solution of team monkeytyping, who finished\nin second place in the YouTube-8M video understanding challenge. The dataset\nused in this challenge is a large-scale benchmark for multi-label video\nclassification. We extend the work in [1] and propose several improvements for\nframe sequence modeling. We propose a network structure called Chaining that\ncan better capture the interactions between labels. Also, we report our\napproaches in dealing with multi-scale information and attention pooling. In\naddition, We find that using the output of model ensemble as a side target in\ntraining can boost single model performance. We report our experiments in\nbagging, boosting, cascade, and stacking, and propose a stacking algorithm\ncalled attention weighted stacking. Our final submission is an ensemble that\nconsists of 74 sub models, all of which are listed in the appendix.","url_abs":"http://arxiv.org/abs/1706.05150v1","url_pdf":"http://arxiv.org/pdf/1706.05150v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-monkeytyping-solution-to-the-youtube-8m","repo_url":"https://github.com/wangheda/youtube-8m","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}